search

huggingface / pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
https://huggingface.co/docs/timm
Apache License 2.0
31.37k stars 4.7k forks source link

can you share hyper-parameters for mixnet? #64

Closed cxxgtxy closed 4 years ago

cxxgtxy commented 4 years ago

Thanks for your impressive work! Can you share your hyper-parameters for mixnet-m (77.256% top 1 reported here.)? Google said they used the same tricks as mnas-net, I cannot reproduce that high top 1 acc following their settings.

rwightman commented 4 years ago

@cxxgtxy I didn't train the s, m, l from scratch, they are fine tuned from TF weights to work with the defaultl BN eps and no SAME padding. The XL I have trained from scratch twice, once with normal color aug, the most recent time with RandAugment. Hparams for the last run are in the README, I still think it can be improved though, if I try one of those again I'll maybe slow the LR decay. I think hparams that have been reported here for training efficientnets should also be reasonable for MixNet.

cxxgtxy commented 4 years ago

Thank you.